You can register for the seminar via HISinOne.


Hyperparameter optimization is a powerful approach to achieve the best performance on many different problems. However, automated approaches to solve this problem tend to ignore the iterative nature of many algorithms. With the dynamic algorithm configuration (DAC) framework we can generalize over prior optimization approaches, as well as handle optimization of hyperparameters that need to be adjusted over multiple time-steps. In this seminar, we will discuss applications (such as temporally extended epsilon greedy exploration in RL) and domains (e.g., reinforcement learning, evolutionary algorithms or deep learning) that can benefit from dynamic configuration methods. A large portion of the seminar will be dedicated to discussing papers that describe DAC methods that employ reinforcement learning to learn hyperparameter optimization policies for various domains.


We require that you have taken lectures on

  • Machine Learning, and/or
  • Deep Learning

We strongly recommend that you have heard lectures on

  • Automated Machine Learning
  • Reinforcement Learning


Every week all students read the relevant literature. Two students will prepare presentations for the topics of the week and present it in the session. After each presentation, we will have time for a question & discussion round and all participants are expected to take part in these. Each student has to write a short paper about their assigned topic which is to be handed in one week after their presentation.


  • Presentation: 40% (20min + 20min Q&A)
  • Paper: 40% (4 pages in AutoML Conf format, due one week after your presentation)
  • Participation in Discussions: 20%


TopicMatriculation NumberAdditional Literature
18.10.2022Introduction of the topic and the available literature--
25.10.2022How to give a good presentation & How to write a report--
01.11.2022No meeting due to a public holiday--
08.11.2022SGDR: Stochastic Gradient Descent with Warm Restarts
15.11.2022Temporally-Extended ε-Greedy Exploration5319822-
22.11.2022Population Based Training of Neural Networks5213721
TempoRL: Learning When to Act4850879
29.11.2022Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits5369037
On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning5349222
06.12.2022Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework5362149-
Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration2330214
13.12.2022Learning Neural Search Policies for Classical Planning4504390-
Tuning the Hyperparameters of Anytime Planning: A Metareasoning Approach with Deep Reinforcement Learning5363937-
20.12.2022Reinforcement learning based adaptive metaheuristics5360110-
Accelerating Quadratic Optimization with Reinforcement Learning5012033-
27.12.2022Christmas Break--
03.01.2023Christmas Break--
10.01.2023A Generalizable Approach to Learning Optimizers4964183-
Multi-Agent Dynamic Algorithm Configuration5250944-


Relevant literature can be found at This list contains many, though not all of the papers that we intend to cover in the seminar.